检索结果-内蒙古大学图书馆

Convergence of energy-based learning in linear resistive networks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huijzer, Anne-Men Chaffey, Thomas Besselink, Bart van Waarde, Henk J. Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Groningen Netherlands CogniGron - Groningen Cognitive Systems and Materials Center Netherlands Control Group Department of Engineering University of Cambridge United Kingdom School of Electrical and Computer Engineering University of Sydney Australia

Energy-based learning algorithms are alternatives to backpropagation and are well-suited to distributed implementations in analog electronic devices. However, a rigorous theory of convergence is lacking. We make a first step in this direction by analysing a particular energy-based learning algorithm, Contrastive Learning, applied to a network of linear adjustable resistors. It is shown that, in this setup, Contrastive Learning is equivalent to projected gradient descent on a convex function, for any step size, giving a guarantee of convergence for the *** Codes 65K10, 68T05, 93B30, 93D99 © 2025, CC BY-SA.

关键词： Contrastive Learning

PDAVIS: Bio-inspired Polarization Event Camera

学校读者我要写书评

暂无评论

PDAVIS: Bio-inspired Polarization Event Camera

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Haessig, Germain Joubert, Damien Haque, Justin Milde, Moritz B. Delbruck, Tobi Gruev, Viktor Center for Vision Automation & Control High-Performance Vision Systems AIT Austrian Institute of Technology Vienna Austria University of Zurich Institute of Neuroinformatics ETH Zurich Switzerland Western Sydney University International Centre for Neuromorphic Systems The MARCS Institute Sydney Australia University of Illinois at Urbana-Champaign Department of Electrical and Computer Engineering UrbanaIL United States

ISBN: (纸本)9798350302493

The stomatopod (mantis shrimp) visual system has recently provided a blueprint for the design of paradigm-shifting polarization and multispectral imaging sensors, enabling solutions to challenging medical and remote sensing problems. However, these bioinspired frame-based cameras lack the high dynamic range and asynchronous polarization vision capabilities of the stomatopod visual system, limiting temporal resolution to ~12ms and dynamic range to ~72dB. Here we present a novel stomatopod-inspired polarization camera which mimics the sustained and transient biological visual pathways to save power and sample data beyond the maximum Nyquist frame rate. This bio-inspired sensor simultaneously captures both synchronous intensity frames and asynchronous polarization brightness change information with submillisecond latencies over a millionfold range of illumination. Our PDAVIS camera is comprised of 346x260 pixels, organized in 2-by-2 macropixels, which filter the incoming light with four linear polarization filters offset by 45°. Polarization information is reconstructed using both low-cost and low-latency event-based algorithms and more accurate but slower deep neural networks. Our sensor is used to image high dynamic range polarization scenes that vary at high speeds and to observe the dynamical properties of single collagen fibers in a bovine tendon under rapid cyclical ***: https://***/mFuCeTMWEqY © 2023 IEEE.

关键词： Polarization

CNL-ResUnet: A novel deep learning architecture for stroke image segmentation

学校读者我要写书评

暂无评论

CNL-ResUnet: A novel deep learning architecture for stroke i...

International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)

作者： Nesrine Jazzar Besma Mabrouk Ali Douik Networked Objects Control and Communication Systems National Engineering School of Sousse University of Sousse Tunisia National Engineering School of Sfax University of Sfax Tunisia Department of Electrical and Computer Engineering Advanced Technologies for Medicine and Signals ATMS National Engineers School Sfax University Tunisia Networked Objects Control and Communication Systems National Engineering School Sousse Tunisia

ISBN: (数字)9798350351484

ISBN: (纸本)9798350351491

Segmentation of stroke lesions holds significant importance in enabling timely diagnosis and subsequent treatment by medical professionals. Automating this process presents technical challenges given the diverse appearance and evolving nature of lesions, discrepancies among medical experts, limited dataset availability, and the necessity for multiple MRI modalities for comprehensive imaging. This research presents an innovative method called CNL-ResUNet, specifically designed for 2D stroke image segmentation. CNL-ResUNet ingeniously incorporates residual blocks into its architecture, capitalizing on their innate capacity to facilitate seamless information flow across layers, thereby empowering the network to efficiently distill complex patterns from sparse datasets. It integrates customized skip connections to reduce semantic disparities between the encoder and decoder layers. Additionally, the architecture incorporates an innovative Classifier and Localizer (CNL) module, providing supplementary classification and localization insights with enhanced accuracy. By combining these insights with the segmentation results, CNL-ResUNet adeptly reduces the occurrence of false positives and false negatives. To evaluate the model’s performance, experiments were conducted utilizing the SISS dataset from the Ischemic Stroke Lesion Segmentation Challenge 2015. The outcomes from these experiments highlight the superiority of our approach, revealing significant qualitative and quantitative improvements across standard evaluation metrics like the Dice coefficient and Accuracy. Our proposed network demonstrates potential for advancing automated tools in stroke segmentation.

关键词： Deep learning Training Image segmentation Accuracy Semantics Stroke (medical condition) Robustness

Discrete-Time Stress Matrix-Based Formation control of General Linear Multi-Agent systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Onuoha, Okechi Kurawa, Suleiman Tang, Zezhi Dong, Yi School of Computing Engineering and Intelligent Systems Ulster University United Kingdom School of Electrical and Electronic Engineering The University of Manchester United Kingdom Department of Automatic Control and Systems Engineering University of Sheffield United Kingdom School of Electronics & Computer Science University of Southampton United Kingdom

This paper considers the distributed leader-follower stress-matrix-based affine formation control problem of discrete-time linear multi-agent systems with static and dynamic leaders. In leader-follower multi-agent formation control, the aim is to drive a set of agents comprising leaders and followers to form any desired geometric pattern and simultaneously execute any required manoeuvre by controlling only a few agents denoted as leaders. Existing works in literature are mostly limited to the cases where the agents’ inter-agent communications are either in the continuous-time settings or the sampled-data cases where the leaders are constrained to constant (or zero) velocities or accelerations. Here, we relax these constraints and study the discrete-time cases where the leaders can have stationary or time-varying velocities. We propose control laws in the study of different situations and provide some sufficient conditions to guarantee the overall system stability. Simulation study is used to demonstrate the efficacy of our proposed control laws. © 2024, CC BY.

关键词： Linear systems

Nonlinear Model Predictive control for Autonomous Sailboat with Optimization of Sail Angle

学校读者我要写书评

暂无评论

Nonlinear Model Predictive Control for Autonomous Sailboat w...

OCEANS 2024 - Halifax, OCEANS 2024

作者： Wu, Junzhuo Pan, Ya-Jun Shen, Chao Smith, Sean Witrant, Emmanuel Dalhousie University Advanced Control and Mechatronics Lab Department of Mechanical Engineering HalifaxB3H 4R2 Canada Carleton University Department of Systems and Computer Engineering OttawaK1S-5B6 Canada Université Grenoble Alpes-CNRS GIPSA-lab GrenobleF-38000 France Dalhousie University Departement of Mechanical Engineering HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9798331540081

This paper studies trajectory tracking control problems of sailing vessels using a nonlinear model predictive control (NMPC) approach with a novel sail angle optimization approach. The proposed sail angle optimization method accounts for physical constraints during practical implementation such as operational sail angle bound and rate of change in sail angles. This technique also emphasizes the potential to use the sail to plan a safe trajectory, while a simple proportional-derivative (PD) controller is used for rudder angle regulation. The NMPC is implemented for trajectory tracking control in the simulation. Results show that the proposed controller can achieve excellent tracking performance in the presence of environmental disturbances in terms of ocean waves. © 2024 IEEE.

关键词： Water waves

A Rolling Horizon Game Considering Network Effect in Cluster Forming for Dynamic Resilient Multiagent systems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Nugraha, Yurid Cetinkaya, Ahmet Hayakawa, Tomohisa Ishii, Hideaki Zhu, Quanyan Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo152-8552 Japan Department of Functional Control Systems Shibaura Institute of Technology Tokyo135-8548 Japan Department of Computer Science Tokyo Insitute of Technology Yokohama226-8502 Japan Department of Electrical and Computer Engineering New York University BrooklynNY11201 United States

A two-player game-theoretic problem on resilient graphs in a multiagent consensus setting is formulated. An attacker is capable to disable some of the edges of the network with the objective to divide the agents into clusters by emitting jamming signals while, in response, the defender recovers some of the edges by increasing the transmission power for the communication signals. Specifically, we consider repeated games between the attacker and the defender where the optimal strategies for the two players are derived in a rolling horizon fashion based on utility functions that take both the agents’ states and the sizes of clusters (known as network effect) into account. The players’ actions at each discrete-time step are constrained by their energy for transmissions of the signals, with a less strict constraint for the attacker. Necessary conditions and sufficient conditions of agent consensus are derived, which are influenced by the energy constraints. The number of clusters of agents at infinite time in the face of attacks and recoveries are also characterized. Simulation results are provided to demonstrate the effects of players’ actions on the cluster forming and to illustrate the players’ performance for different horizon parameters. © 2023, CC BY.

关键词： Game theory

Unveiling drug-induced side effects through network-based analysis: an update

学校读者我要写书评

暂无评论

Unveiling drug-induced side effects through network-based an...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Alessio Funari Federica Conte Paola Paci Department of Translational and Precision Medicine Sapienza University of Rome Institute for Systems Analysis and Computer Science “Antonio Ruberti” National Research Council Rome Italy Institute for Systems Analysis and Computer Science “Antonio Ruberti” National Research Council Rome Italy Department of Computer Control and Management Engineering Sapienza University of Rome Rome Italy

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

In this article, we propose an updated version of our previously developed model for predicting drug-side effect associations, applied to two case studies: long QT syndrome and asthma. The classifier accepts the name of a specific drug side effect as input and outputs a list of drugs potentially associated with this side effect. By simulating how drug effects propagate within the interactome using the Random Walk with Restart algorithm, the classifier identifies genes potentially associated with the onset of the side effect. Based on the rationale that the more a drug perturbs these genes, the more likely it is to cause the side effect, the model identifies drugs potentially linked to the onset of the side effect. Moreover, the model enables the categorization of drugs into chemical subclasses using the ClassyFire schema, facilitating the analysis of complex side effects, such as asthma, through more specific mechanisms. The results show that the model identifies both drugs known to be associated with certain side effects, as well as drugs not officially reported by the FDA, demonstrating its generalizability and practical relevance. This method is also adaptable for analyzing other side effects.

关键词： Drugs Analytical models Adaptation models Predictive models Classification algorithms Bioinformatics Chemicals Asthma

Distributed Optimization via Gradient Descent with Event-Triggered Zooming Over Quantized Communication

学校读者我要写书评

暂无评论

Distributed Optimization via Gradient Descent with Event-Tri...

IEEE Conference on Decision and control

作者： Apostolos I. Rikos Wei Jiang Themistoklis Charalambous Karl H. Johansson Department of Electrical and Computer Engineering Division of Systems Engineering Boston University Boston MA US Department of Electrical and Computer Engineering School of Engineering University of Cyprus Aalto University Nicosia Cyprus Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland Division of Decision and Control Systems KTH Royal Institute of Technologyy Stockholm Sweden

In this paper, we study unconstrained distributed optimization strongly convex problems, in which the exchange of information in the network is captured by a directed graph topology over digital channels that have limited capacity (and hence information should be quantized). Distributed methods in which nodes use quantized communication yield a solution at the proximity of the optimal solution, hence reaching an error floor that depends on the quantization level used; the finer the quantization the lower the error floor. However, it is not possible to determine in advance the optimal quantization level that ensures specific performance guarantees (such as achieving an error floor below a predefined threshold). Choosing a very small quantization level that would guarantee the desired performance, requires information packets of very large size, which is not desirable (could increase the probability of packet losses, increase delays, etc) and often not feasible due to the limited capacity of the channels available. In order to obtain a communication-efficient distributed solution and a sufficiently close proximity to the optimal solution, we propose a quantized distributed optimization algorithm that converges in a finite number of steps and is able to adjust the quantization level accordingly. The proposed solution uses a finite-time distributed optimization protocol to find a solution to the problem for a given quantization level in a finite number of steps and keeps refining the quantization level until the difference in the solution between two successive solutions with different quantization levels is below a certain pre-specified threshold. Therefore, the proposed algorithm progressively refines the quantization level, thus eventually achieving low error floor with a reduced communication burden. The performance gains of the proposed algorithm are demonstrated via illustrative examples.

关键词：

Performance Analysis of Distributed Filtering under Mismatched Noise Covariances

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lyu, Xiaoxu Wen, Guanghui Shi, Ling Duan, Peihu Duan, Zhisheng The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong The Laboratory of Security Operation and Control for Intelligent Autonomous Systems Department of Systems Science School of Mathematics Southeast University Nanjing211189 China School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering Science College of Engineering Peking University Beijing100871 China

This paper systematically investigates the performance of consensus-based distributed filtering under mismatched noise covariances. First, we introduce three performance evaluation indices for such filtering problems, namely the standard performance evaluation index, the nominal performance evaluation index, and the estimation error covariance. We derive difference expressions among these indices and establish one-step relations among them under various mismatched noise covariance scenarios. We particularly reveal the effect of the consensus fusion on these relations. Furthermore, the recursive relations are introduced by extending the results of the one-step relations. Subsequently, we demonstrate the convergence of these indices under the collective observability condition, and show this convergence condition of the nominal performance evaluation index can guarantee the convergence of the estimation error covariance. Additionally, we prove that the estimation error covariance of the consensus-based distributed filter under mismatched noise covariances can be bounded by the Frobenius norms of the noise covariance deviations and the trace of the nominal performance evaluation index. Finally, the effectiveness of the theoretical results is verified by numerical simulations. Copyright © 2024, The Authors. All rights reserved.

关键词： Wiener filtering